Model page

TheBloke/Chronolima-Airo-Grad-L2-13B-GGML warn

Weights only ship in a format that can run code when loaded; its license differs from its base model's.

Could not load this model from the Hugging Face API (private, gated, or nonexistent). Findings below are from our archive.

Scan coverageStatic battery2026-08-25Weights batteryqueuedBehavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-25
Weights batteryWeights forensics — no GPU, no downloadqueued
Behavioral batteryLive-inference differentialsnot run

Ingot runs three batteries against a model. What each one checks →

Findings

Scanned 2026-08-25 · published from a community scan.

medium Pickle-serialized weights, no safetensors

Weights ship only as pickle-based files (chronolima-airo-grad-l2-13b.ggmlv3.q2_K.bin, chronolima-airo-grad-l2-13b.ggmlv3.q3_K_L.bin, chronolima-airo-grad-l2-13b.ggmlv3.q3_K_M.bin, …). Loading pickle executes arbitrary code from the file — prefer a safetensors release or load in a sandbox.

How to fix

Convert the weights to safetensors before loading them anywhere that matters.

  1. Do not load the pickle files in-process — pickle deserialization executes arbitrary code from the file.
  2. Convert locally in a sandbox: `pip install safetensors` and use `safetensors.torch.save_file` on a state dict loaded with `torch.load(..., weights_only=True)` (refuses most code-execution payloads), or use Hugging Face's `convert.py` space/script.
  3. Pin the exact revision hash you converted from, and load only your converted safetensors artifact from then on.

medium License differs from claimed parent (llama2 vs agpl-3.0)

This model declares llama2 while its claimed base kingbri/chronolima-airo-grad-l2-13B declares agpl-3.0. Verify the re-license is permitted before commercial use.

How to fix

Verify the re-license is actually permitted before relying on it.

  1. Read the parent's license for derivative-work and re-licensing terms — many open-weight licenses (e.g. Llama-family) do not permit arbitrary re-licensing.
  2. If the re-license is not permitted, the parent's terms govern your use regardless of what this repo declares.

Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.

Fingerprint

The durable profile of this model: measured weights-and-metadata facts, rebuilt on every scan and battery run. Updated 2026-08-25.

architecturellama
licensellama2
serializationno safetensors pickle
chat templatenone
claimed lineagekingbri/chronolima-airo-grad-l2-13B
lineage verifiedunverified — weights battery pending
Full measured fingerprint
librarytransformers
pipelinetext-generation
repo files20 — pickle: chronolima-airo-grad-l2-13b.ggmlv3.q2_K.bin, chronolima-airo-grad-l2-13b.ggmlv3.q3_K_L.bin, chronolima-airo-grad-l2-13b.ggmlv3.q3_K_M.bin, chronolima-airo-grad-l2-13b.ggmlv3.q3_K_S.bin, chronolima-airo-grad-l2-13b.ggmlv3.q4_0.bin, chronolima-airo-grad-l2-13b.ggmlv3.q4_1.bin, chronolima-airo-grad-l2-13b.ggmlv3.q4_K_M.bin, chronolima-airo-grad-l2-13b.ggmlv3.q4_K_S.bin, chronolima-airo-grad-l2-13b.ggmlv3.q5_0.bin, chronolima-airo-grad-l2-13b.ggmlv3.q5_1.bin
revisionb1e19c8e4c50
HF snapshot15 downloads · 3 likes · updated 2023-09-27 · captured 2026-08-25
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightsqueued2026-08-25 22:280

Verdict badge

Ship the verdict in your README — it always shows the latest published analysis:

Ingot verdict: warn

[![Ingot scan](https://ingot.tools/api/v1/models/TheBloke/Chronolima-Airo-Grad-L2-13B-GGML/badge.svg)](https://ingot.tools/models/TheBloke/Chronolima-Airo-Grad-L2-13B-GGML)
Gate it in CI